Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2021. Min Act: -0.0001

Data Index: 37139 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.2190. Min Act: -0.0001

Data Index: 564703 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1447. Min Act: -0.0001

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1491. Min Act: -0.0001

Data Index: 882508 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1490. Min Act: -0.0001

Data Index: 859474 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1427. Min Act: -0.0001

Data Index: 414855 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1409. Min Act: -0.0001

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1043030 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1336. Min Act: -0.0001

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1337. Min Act: -0.0001

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1378. Min Act: -0.0001

Data Index: 652320 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1313. Min Act: -0.0001

Data Index: 34620 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1403. Min Act: -0.0001

Data Index: 925561 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1345. Min Act: -0.0001

Data Index: 515410 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1118. Min Act: -0.0001

Data Index: 344137 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1289. Min Act: -0.0001

Data Index: 908149 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1407. Min Act: -0.0001

Data Index: 683211 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1314. Min Act: -0.0001

Data Index: 494998 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1245. Min Act: -0.0001

Data Index: 473252 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.2190. Min Range: -0.2190

Max Act: 0.1240. Min Act: -0.0001

Data Index: 204260 (C4 (Web Text))

Max Activating Token Index: 883